Causal Explanations for Image Classifiers
Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to extract them. However, none of the existing tools use a principled approach based on formal definitions of causes and explanations for the explanation extraction. In this paper we present a novel black-box approach to computing explanations grounded in the theory of actual causality. We prove relevant theoretical results and present an algorithm for computing approximate explanations based on these definitions. We prove termination of our algorithm and discuss its complexity and the amount of approximation compared to the precise definition. We implemented the framework in a tool rex and we present experimental results and a comparison with state-of-the-art tools. We demonstrate that rex is the most efficient tool and produces the smallest explanations, in addition to outperforming other black-box tools on standard quality measures.
Code (1)
Similar Papers 제목 키워드 기반
Sufficient, Necessary and Complete Causal Explanations in Image Classification
Existing algorithms for explaining the outputs of image classifiers are based on a variety of approaches and produce explanations that frequently lack formal rigour. On the other hand, logic-based explanations are formal…
Image ClassificationExplaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in p…
AttributecounterfactualDecision MakingCausal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Dataset
In this paper, we propose leveraging causal generative learning as an interpretable tool for explaining image classifiers. Specifically, we present a generative counterfactual inference approach to study the influence of…
AttributecounterfactualCounterfactual ExplanationCounterfactual InferenceGenerative causal explanations of black-box classifiers
We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent …
Multiple Different Black Box Explanations for Image Classifiers
Existing explanation tools for image classifiers usually give only a single explanation for an image's classification. For many images, however, both humans and image classifiers accept more than one explanation for the …